[gcc r13-4272] i386: Only enable small loop unrolling in backend [PR 107692]

[gcc r13-4272] i386: Only enable small loop unrolling in backend [PR 107692]

[Hongyu Wang]

https://gcc.gnu.org/g:8caf155a3d6e23e47bf55068ad23c23d4655a054

commit r13-4272-g8caf155a3d6e23e47bf55068ad23c23d4655a054
Author: Hongyu Wang <hongyu.wang@intel.com>
Date:   Sat Nov 19 09:38:00 2022 +0800

    i386: Only enable small loop unrolling in backend [PR 107692]
    
    Followed by the discussion in pr107692, -munroll-only-small-loops
    Does not turns on/off -funroll-loops, and current check in
    pass_rtl_unroll_loops::gate would cause -fno-unroll-loops do not take
    effect. Revert the change about targetm.loop_unroll_adjust and apply
    the backend option change to strictly follow the rule that
    -funroll-loops takes full control of loop unrolling, and
    munroll-only-small-loops just change its behavior to unroll small size
    loops.
    
    gcc/ChangeLog:
    
            PR target/107692
            * common/config/i386/i386-common.cc (ix86_optimization_table):
            Enable loop unroll O2, disable -fweb and -frename-registers
            by default.
            * config/i386/i386-options.cc
            (ix86_override_options_after_change):
            Disable small loop unroll when funroll-loops enabled, reset
            cunroll_grow_size when it is not explicitly enabled.
            (ix86_option_override_internal): Call
            ix86_override_options_after_change instead of calling
            ix86_recompute_optlev_based_flags and ix86_default_align
            separately.
            * config/i386/i386.cc (ix86_loop_unroll_adjust): Adjust unroll
            factor if -munroll-only-small-loops enabled.
            * loop-init.cc (pass_rtl_unroll_loops::gate): Do not enable
            loop unrolling for -O2-speed.
            (pass_rtl_unroll_loops::execute): Rmove
            targetm.loop_unroll_adjust check.
    
    gcc/testsuite/ChangeLog:
    
            PR target/107692
            * gcc.dg/guality/loop-1.c: Remove additional option for ia32.
            * gcc.target/i386/pr86270.c: Add -fno-unroll-loops.
            * gcc.target/i386/pr93002.c: Likewise.

Diff:
---
 gcc/common/config/i386/i386-common.cc   |  8 ++++++++
 gcc/config/i386/i386-options.cc         | 34 +++++++++++++++++++++++++++++----
 gcc/config/i386/i386.cc                 | 18 +++++------------
 gcc/loop-init.cc                        | 11 ++++-------
 gcc/testsuite/gcc.dg/guality/loop-1.c   |  2 --
 gcc/testsuite/gcc.target/i386/pr86270.c |  2 +-
 gcc/testsuite/gcc.target/i386/pr93002.c |  2 +-
 7 files changed, 49 insertions(+), 28 deletions(-)

diff --git a/gcc/common/config/i386/i386-common.cc b/gcc/common/config/i386/i386-common.cc
index 6ce2a588adc..660a977b68b 100644
--- a/gcc/common/config/i386/i386-common.cc
+++ b/gcc/common/config/i386/i386-common.cc
@@ -1808,7 +1808,15 @@ static const struct default_options ix86_option_optimization_table[] =
     /* The STC algorithm produces the smallest code at -Os, for x86.  */
     { OPT_LEVELS_2_PLUS, OPT_freorder_blocks_algorithm_, NULL,
       REORDER_BLOCKS_ALGORITHM_STC },
+
+    /* Turn on -funroll-loops with -munroll-only-small-loops to enable small
+       loop unrolling at -O2.  */
+    { OPT_LEVELS_2_PLUS_SPEED_ONLY, OPT_funroll_loops, NULL, 1 },
     { OPT_LEVELS_2_PLUS_SPEED_ONLY, OPT_munroll_only_small_loops, NULL, 1 },
+    /* Turns off -frename-registers and -fweb which are enabled by
+       funroll-loops.  */
+    { OPT_LEVELS_ALL, OPT_frename_registers, NULL, 0 },
+    { OPT_LEVELS_ALL, OPT_fweb, NULL, 0 },
     /* Turn off -fschedule-insns by default.  It tends to make the
        problem with not enough registers even worse.  */
     { OPT_LEVELS_ALL, OPT_fschedule_insns, NULL, 0 },
diff --git a/gcc/config/i386/i386-options.cc b/gcc/config/i386/i386-options.cc
index e5c77f3a84d..bc1d36e36a8 100644
--- a/gcc/config/i386/i386-options.cc
+++ b/gcc/config/i386/i386-options.cc
@@ -1838,8 +1838,37 @@ ix86_recompute_optlev_based_flags (struct gcc_options *opts,
 void
 ix86_override_options_after_change (void)
 {
+  /* Default align_* from the processor table.  */
   ix86_default_align (&global_options);
+
   ix86_recompute_optlev_based_flags (&global_options, &global_options_set);
+
+  /* Disable unrolling small loops when there's explicit
+     -f{,no}unroll-loop.  */
+  if ((OPTION_SET_P (flag_unroll_loops))
+     || (OPTION_SET_P (flag_unroll_all_loops)
+	 && flag_unroll_all_loops))
+    {
+      if (!OPTION_SET_P (ix86_unroll_only_small_loops))
+	ix86_unroll_only_small_loops = 0;
+      /* Re-enable -frename-registers and -fweb if funroll-loops
+	 enabled.  */
+      if (!OPTION_SET_P (flag_web))
+	flag_web = flag_unroll_loops;
+      if (!OPTION_SET_P (flag_rename_registers))
+	flag_rename_registers = flag_unroll_loops;
+      /* -fcunroll-grow-size default follws -f[no]-unroll-loops.  */
+      if (!OPTION_SET_P (flag_cunroll_grow_size))
+	flag_cunroll_grow_size = flag_unroll_loops
+				 || flag_peel_loops
+				 || optimize >= 3;
+    }
+  else
+    {
+      if (!OPTION_SET_P (flag_cunroll_grow_size))
+	flag_cunroll_grow_size = flag_peel_loops || optimize >= 3;
+    }
+
 }
 
 /* Clear stack slot assignments remembered from previous functions.
@@ -2351,7 +2380,7 @@ ix86_option_override_internal (bool main_args_p,
 
   set_ix86_tune_features (opts, ix86_tune, opts->x_ix86_dump_tunes);
 
-  ix86_recompute_optlev_based_flags (opts, opts_set);
+  ix86_override_options_after_change ();
 
   ix86_tune_cost = processor_cost_table[ix86_tune];
   /* TODO: ix86_cost should be chosen at instruction or function granuality
@@ -2382,9 +2411,6 @@ ix86_option_override_internal (bool main_args_p,
       || TARGET_64BIT_P (opts->x_ix86_isa_flags))
     opts->x_ix86_regparm = REGPARM_MAX;
 
-  /* Default align_* from the processor table.  */
-  ix86_default_align (opts);
-
   /* Provide default for -mbranch-cost= value.  */
   SET_OPTION_IF_UNSET (opts, opts_set, ix86_branch_cost,
 		       ix86_tune_cost->branch_cost);
diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 14719d397a4..881cd9f3bb7 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -23828,20 +23828,12 @@ ix86_loop_unroll_adjust (unsigned nunroll, class loop *loop)
 
   /* Unroll small size loop when unroll factor is not explicitly
      specified.  */
-  if (!(flag_unroll_loops
-	|| flag_unroll_all_loops
-	|| loop->unroll))
+  if (ix86_unroll_only_small_loops && !loop->unroll)
     {
-      nunroll = 1;
-
-      /* Any explicit -f{no-}unroll-{all-}loops turns off
-	 -munroll-only-small-loops.  */
-      if (ix86_unroll_only_small_loops
-	  && !OPTION_SET_P (flag_unroll_loops)
-	  && loop->ninsns <= ix86_cost->small_unroll_ninsns)
-	nunroll = ix86_cost->small_unroll_factor;
-
-      return nunroll;
+      if (loop->ninsns <= ix86_cost->small_unroll_ninsns)
+	return MIN (nunroll, ix86_cost->small_unroll_factor);
+      else
+	return 1;
     }
 
   if (!TARGET_ADJUST_UNROLL)
diff --git a/gcc/loop-init.cc b/gcc/loop-init.cc
index 9789efa1e11..f03c077cae1 100644
--- a/gcc/loop-init.cc
+++ b/gcc/loop-init.cc
@@ -565,12 +565,10 @@ public:
   {}
 
   /* opt_pass methods: */
-  bool gate (function *fun) final override
+  bool gate (function *) final override
     {
-      return (flag_unroll_loops || flag_unroll_all_loops || cfun->has_unroll
-	      || (targetm.loop_unroll_adjust
-		  && optimize >= 2
-		  && optimize_function_for_speed_p (fun)));
+      return (flag_unroll_loops || flag_unroll_all_loops
+	      || cfun->has_unroll);
     }
 
   unsigned int execute (function *) final override;
@@ -586,8 +584,7 @@ pass_rtl_unroll_loops::execute (function *fun)
       if (dump_file)
 	df_dump (dump_file);
 
-      if (flag_unroll_loops
-	  || targetm.loop_unroll_adjust)
+      if (flag_unroll_loops)
 	flags |= UAP_UNROLL;
       if (flag_unroll_all_loops)
 	flags |= UAP_UNROLL_ALL;
diff --git a/gcc/testsuite/gcc.dg/guality/loop-1.c b/gcc/testsuite/gcc.dg/guality/loop-1.c
index a32ea445a3f..1b1f6d32271 100644
--- a/gcc/testsuite/gcc.dg/guality/loop-1.c
+++ b/gcc/testsuite/gcc.dg/guality/loop-1.c
@@ -1,7 +1,5 @@
 /* { dg-do run } */
 /* { dg-options "-fno-tree-scev-cprop -fno-tree-vectorize -g" } */
-/* { dg-additional-options "-mno-unroll-only-small-loops" { target ia32 } } */
-
 
 #include "../nop.h"
 
diff --git a/gcc/testsuite/gcc.target/i386/pr86270.c b/gcc/testsuite/gcc.target/i386/pr86270.c
index cbc9fbb0450..98b012caf23 100644
--- a/gcc/testsuite/gcc.target/i386/pr86270.c
+++ b/gcc/testsuite/gcc.target/i386/pr86270.c
@@ -1,5 +1,5 @@
 /* { dg-do compile } */
-/* { dg-options "-O2 -mno-unroll-only-small-loops" } */
+/* { dg-options "-O2 -fno-unroll-loops" } */
 
 int *a;
 long len;
diff --git a/gcc/testsuite/gcc.target/i386/pr93002.c b/gcc/testsuite/gcc.target/i386/pr93002.c
index f75a847f75d..7e2d869e17b 100644
--- a/gcc/testsuite/gcc.target/i386/pr93002.c
+++ b/gcc/testsuite/gcc.target/i386/pr93002.c
@@ -1,6 +1,6 @@
 /* PR target/93002 */
 /* { dg-do compile } */
-/* { dg-options "-O2 -mno-unroll-only-small-loops" } */
+/* { dg-options "-O2 -fno-unroll-loops" } */
 /* { dg-final { scan-assembler-not "cmp\[^\n\r]*-1" } } */
 
 volatile int sink;